optimize LEA

- go inlining
- optimized AMD64 using github.com/minio/c2goasm
- support arm64 NEON using github.com/gorse-io/goat
  - tested in Mac Mini M1

.gitignore

@@ -1,5 +1,5 @@
-# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,windows,linux,go
-# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,windows,linux,go
+# Created by https://www.toptal.com/developers/gitignore/api/go,linux,windows,visualstudiocode,macos
+# Edit at https://www.toptal.com/developers/gitignore?templates=go,linux,windows,visualstudiocode,macos
 
 ### Go ###
 # If you prefer the allow list template instead of the deny list, see community template:
@@ -39,6 +39,39 @@ go.work
 # .nfs files are created when an open file is removed but is still being accessed
 .nfs*
 
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
 ### VisualStudioCode ###
 .vscode/*
 !.vscode/settings.json
@@ -84,4 +117,4 @@ $RECYCLE.BIN/
 # Windows shortcuts
 *.lnk
 
-# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,windows,linux,go
+# End of https://www.toptal.com/developers/gitignore/api/go,linux,windows,visualstudiocode,macos

lea/READMD.md

@@ -0,0 +1 @@
+# [Source Code](https://seed.kisa.or.kr/kisa/Board/20/detailView.do)

lea/amd64_c2goasm/.gitignore

@@ -0,0 +1,2 @@
+*.s
+*.o

lea/amd64_c2goasm/Makefile

@@ -0,0 +1,28 @@
+EXECUTABLES=clang c2goasm asm2plan9s asmfmt as yasm
+K := $(foreach exec,$(EXECUTABLES),\
+        $(if $(shell which $(exec)),some string,$(error "No $(exec) in PATH")))
+
+C2GOASM=c2goasm
+
+CC=clang
+CFLAGS=-O3 -fno-asynchronous-unwind-tables -fno-exceptions -fno-rtti -mno-red-zone -mstackrealign -mllvm -inline-threshold=1000
+CFLAGS_ARCH=-arch x86_64 -masm=intel
+
+CFLAGS_SSE2=-msse -msse2
+CFLAGS_SSSE3=${CFLAGS_SSE2} -mssse3
+CFLAGS_AVX2=${CFLAGS_SSSE3} -mavx -mavx2
+
+
+all: sse2 avx2 init
+
+sse2: 
+	${CC} ${CFLAGS} ${CFLAGS_ARCH} ${CFLAGS_SSE2} -S src/lea_sse2.c -o src/lea_sse2.s
+	${C2GOASM} -a -f src/lea_sse2.s lea_amd64_sse2.s
+
+avx2:
+	${CC} ${CFLAGS} ${CFLAGS_ARCH} ${CFLAGS_AVX2} -S src/lea_avx2.c -o src/lea_avx2.s
+	${C2GOASM} -a -f src/lea_avx2.s lea_amd64_avx2.s
+
+init:
+	${CC} ${CFLAGS} ${CFLAGS_ARCH} ${CFLAGS_SSE2} -S src/lea_init.c -o src/lea_init.s
+	${C2GOASM} -a -f src/lea_init.s lea_init.s

lea/amd64_c2goasm/lea_amd64_avx2.go

@@ -0,0 +1,11 @@
+//go:build amd64 && gc && !purego
+
+package lea
+
+import "unsafe"
+
+//go:noescape
+func __lea_encrypt_8block(ct, pt, rk unsafe.Pointer, round uint64)
+
+//go:noescape
+func __lea_decrypt_8block(pt, ct, rk unsafe.Pointer, round uint64)

lea/amd64_c2goasm/lea_amd64_sse2.go

@@ -0,0 +1,11 @@
+//go:build amd64 && gc && !purego
+
+package lea
+
+import "unsafe"
+
+//go:noescape
+func __lea_encrypt_4block(ct, pt, rk unsafe.Pointer, round uint64)
+
+//go:noescape
+func __lea_decrypt_4block(pt, ct, rk unsafe.Pointer, round uint64)